{"id":"W1985300676","doi":"10.1371/journal.pone.0094308","title":"Sequential Decisions: A Computational Comparison of Observational and Reinforcement Accounts","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Reinforcement learning; Reinforcement; Artificial intelligence; Machine learning; Computer science; Cognitive psychology; Computational model; Observational study; Brain activity and meditation; Principle of maximum entropy; Sequence (biology); Entropy (arrow of time); Psychology; Neuroscience; Electroencephalography; Mathematics; Social psychology; Biology; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002839365,0.00005592165,0.0001317661,0.00007507766,0.00009253505,0.00005950556,0.0002436894,0.00001901525,0.00001644892],"category_scores_gemma":[0.000237867,0.00005416851,0.00001776103,0.0001897654,0.00005670038,0.0003828479,0.0001939601,0.00004604159,0.00001498037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001295527,"about_ca_system_score_gemma":0.00004966292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006368545,"about_ca_topic_score_gemma":0.00000284935,"domain_scores_codex":[0.9989275,0.00002477385,0.000214909,0.0001784221,0.0005461918,0.0001081754],"domain_scores_gemma":[0.9992099,0.0002710553,0.00009697393,0.0001235431,0.0002521885,0.00004632311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004701038,0.002327345,0.1554338,0.0001468428,0.0002719521,0.000002010854,0.004370887,0.009648998,0.03930119,0.6712311,0.0009619325,0.1162569],"study_design_scores_gemma":[0.000364247,0.0001068257,0.05622315,0.0001554964,0.00001242725,7.613766e-7,0.00002957736,0.9196458,0.004312003,0.01890626,0.0001410394,0.000102411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3907063,0.00002011746,0.6078914,0.0003931457,0.0000296014,0.00008984464,0.000001750334,0.00002011273,0.0008476861],"genre_scores_gemma":[0.9137995,0.000003996919,0.08581417,0.0003033412,0.00002622725,0.000004379306,0.000007377902,0.000001565262,0.00003949364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9099968,"threshold_uncertainty_score":0.2208928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2167956337841406,"score_gpt":0.3206670283755635,"score_spread":0.1038713945914229,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}